© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11272
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with sadness and crying

    oai_token-act-pair · gemini-2.0-flash

    crying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.77
    المشاركات
    -0.77
     ProtoMessage
    -0.75
    AndEndTag
    -0.71
    PhysRevD
    -0.66
     <<<<<<<<<<<<<<
    -0.63
    providedIn
    -0.62
     nahilalakip
    -0.61
    HasColumnName
    -0.60
    ModelAdmin
    -0.60
    POSITIVE LOGITS
     emotional
    0.76
     emotionally
    0.75
    Emotional
    0.60
    emotional
    0.60
     Emotional
    0.59
     emo
    0.59
     emocional
    0.57
     sentimental
    0.55
     emotion
    0.54
     Emotion
    0.50
    Activations Density 0.041%

    No Known Activations